Explainability Auditing for Intelligent Systems: A Rationale for Multi-Disciplinary Perspectives
Preprint
Abstract
National and international guidelines for trustworthy artificial intelligence (AI) consider explainability to be a central facet of trustworthy systems. This paper outlines a multi-disciplinary rationale for explainability auditing. Specifically, we propose that explainability auditing can ensure the quality of explainability of systems in applied contexts and can be the basis for certification as a means to communicate whether systems meet certain explainability standards and requirements. Moreover, we emphasize that explainability auditing needs to take a multi-disciplinary perspective, and we provide an overview of four perspectives (technical, psychological, ethical, legal) and their respective benefits with respect to explainability auditing.Keywords
All Related Versions
This publication has 21 references indexed in Scilit:
- What do we want from Explainable Artificial Intelligence (XAI)? – A stakeholder perspective on XAI and a conceptual model guiding interdisciplinary XAI researchArtificial Intelligence, 2021
- Ethics-Based Auditing to Develop Trustworthy AIMinds and Machines, 2021
- Explainability as a non-functional requirement: challenges and recommendationsRequirements Engineering, 2020
- The Ethics of AI Ethics: An Evaluation of GuidelinesMinds and Machines, 2020
- A Misdirected Principle with a Catch: Explicability for AIMinds and Machines, 2019
- The Pragmatic Turn in Explainable Artificial Intelligence (XAI)Minds and Machines, 2019
- Explanation in artificial intelligence: Insights from the social sciencesArtificial Intelligence, 2019
- Fair, Transparent, and Accountable Algorithmic Decision-making ProcessesPhilosophy & Technology, 2017
- Taking reading comprehension exams on screen or on paper? A metacognitive analysis of learning texts under time pressureComputers in Human Behavior, 2012
- Explanation and trust: what to tell the user in security and AI?Ethics and Information Technology, 2010